Fault Diagnosis of Rolling Bearing Based on Variational Mode Decomposition and Improved Canberra Distance in Symmetrized Dot Pattern Image

Abstract

The classification of time series is an important work in mechanical fault diagnosis. In recent years, image-based signal processing methods have been widely used in bearing fault diagnosis. However, there are still some problems in the signal classification of multiple fault types and weak fault characteristics. In order to improve the classification accuracy of time series, a diagnosis method based on variable mode decomposition (VMD) and improved Canberra distance is proposed. In this method, the decomposed signal is first converted into a symmetrized dot pattern. Then the image features are extracted using Canberra distance and maximum eigenvalue. Through the obtained features, the accurate diagnosis of bearing vibration signal is realized. The experimental results show that the improved Canberra distance has high classification accuracy.